Make long-running FMA archive progress legible at a glance

Constraint: Multi-session continuation gets brittle when large real-data downloads require manual byte math to estimate progress
Rejected: Leave inspect output as raw archive size only | Forces every future session to recalculate completion state by hand
Confidence: high
Scope-risk: narrow
Directive: Keep progress fields stable so handoff tooling and humans can rely on them during long archive transfers
Tested: /usr/local/miniconda3/bin/python -m py_compile acr-engine/scripts/prepare_fma_archive.py; /usr/local/miniconda3/bin/python acr-engine/scripts/prepare_fma_archive.py inspect
Not-tested: Completion of the full archive and downstream extraction remain pending

@@ -9,6 +9,7 @@ import subprocess
 from pathlib import Path
 from pathlib import Path
 
 
 FMA_SMALL_URL = "https://modelscope.cn/datasets/pengzhendong/fma/resolve/master/fma_small.zip"
 FMA_SMALL_URL = "https://modelscope.cn/datasets/pengzhendong/fma/resolve/master/fma_small.zip"
+FMA_SMALL_BYTES = 7679594875
 ARCHIVE_PATH = Path("data/raw/fma_small.zip")
 ARCHIVE_PATH = Path("data/raw/fma_small.zip")
 EXTRACT_DIR = Path("data/raw/fma_small_audio")
 EXTRACT_DIR = Path("data/raw/fma_small_audio")
 
 
@@ -42,12 +43,17 @@ def inspect() -> dict:
     num_audio = 0
     num_audio = 0
     if extract_exists:
     if extract_exists:
         num_audio = len([p for p in EXTRACT_DIR.rglob('*') if p.suffix.lower() in {'.mp3', '.wav', '.flac', '.ogg'}])
         num_audio = len([p for p in EXTRACT_DIR.rglob('*') if p.suffix.lower() in {'.mp3', '.wav', '.flac', '.ogg'}])
+    archive_size = ARCHIVE_PATH.stat().st_size if archive_exists else 0
+    progress_ratio = (archive_size / FMA_SMALL_BYTES) if archive_exists and FMA_SMALL_BYTES else 0.0
     return {
     return {
         "action": "inspect",
         "action": "inspect",
         "archive_url": FMA_SMALL_URL,
         "archive_url": FMA_SMALL_URL,
+        "archive_bytes_expected": FMA_SMALL_BYTES,
         "archive_path": str(ARCHIVE_PATH.resolve()),
         "archive_path": str(ARCHIVE_PATH.resolve()),
         "archive_exists": archive_exists,
         "archive_exists": archive_exists,
-        "archive_size": ARCHIVE_PATH.stat().st_size if archive_exists else 0,
+        "archive_size": archive_size,
+        "archive_progress_ratio": round(progress_ratio, 6),
+        "archive_progress_percent": round(progress_ratio * 100, 4),
         "extract_dir": str(EXTRACT_DIR.resolve()),
         "extract_dir": str(EXTRACT_DIR.resolve()),
         "extract_exists": extract_exists,
         "extract_exists": extract_exists,
         "num_audio_files": num_audio,
         "num_audio_files": num_audio,

@@ -230,6 +230,27 @@
 
 
 
 
 
 
+
+### Stage: FMA 下载进度可视化
+
+完成项：
+- 增强 [acr-engine/scripts/prepare_fma_archive.py](../acr-engine/scripts/prepare_fma_archive.py) 的 `inspect` 输出
+- 新增：
+  - `archive_bytes_expected`
+  - `archive_progress_ratio`
+  - `archive_progress_percent`
+
+验证结果：
+- `/usr/local/miniconda3/bin/python -m py_compile scripts/prepare_fma_archive.py` 成功
+- `/usr/local/miniconda3/bin/python scripts/prepare_fma_archive.py inspect` 成功
+- 当前结果：
+  - `archive_size=61550592`
+  - `archive_progress_percent=0.8015`
+
+结论：
+- 新 session 现在不需要手工换算大包下载进度
+- 长时间 FMA 下载的交接成本进一步降低
+
 ### Stage: FMA 源切换到 ModelScope
 ### Stage: FMA 源切换到 ModelScope
 
 
 完成项：
 完成项：